CN103065283A - Adherence separation algorithm of intensive solid state nuclear tracks - Google Patents
Adherence separation algorithm of intensive solid state nuclear tracks Download PDFInfo
- Publication number
- CN103065283A CN103065283A CN2012105842948A CN201210584294A CN103065283A CN 103065283 A CN103065283 A CN 103065283A CN 2012105842948 A CN2012105842948 A CN 2012105842948A CN 201210584294 A CN201210584294 A CN 201210584294A CN 103065283 A CN103065283 A CN 103065283A
- Authority
- CN
- China
- Prior art keywords
- track
- hole
- profile
- image
- connected region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses an adherence separation algorithm of intensive solid state nuclear tracks. The adherence separation algorithm of the intensive solid state nuclear tracks includes the following steps: (1) image contrast enhancing; (2) expanding maximum value separation; (3) area proportion adherence separation; and (4) special adherence separation. The adherence separation algorithm of the intensive solid state nuclear tracks can effectively solve the problems of removing of noise and non-track impurities in track images, processing of the tracks which are large in granularity difference, accurate separation of the tracks which are serious in adherence and uneven in inner gray scale, and meanwhile promote the speed of adherence separation.
Description
Technical field
The invention belongs to technical field of image processing, relate generally to a kind of packed solid nuclear track micro-image adherence Separation algorithm, its design utilizes Mathematical Morphology Method, at first degree of comparing strengthens to process light grey little track, cut apart again to obtain the base profile of track and remove non-track impurity, carry out at last adherence Separation to obtain the accurate profile of single track.
Background technology
When high energy charged particles enters solid material, can stay the radiation damage of nanometer scale along its track, through forming the solid state nuclear track that to use microscopic after the etch processes.Can determine kind, power spectrum and the yield of charged particle by number, size, shape and the degree of depth of measuring track.The track that produces on the track sheet is ten hundreds of, and diameter is from several microns to tens microns, and human eye carries out interpretation and extremely inconvenience of statistics by microscope.Mainly adopt at present the high precision microscopic system that track is carried out numeral and take pictures, then analyze and process obtaining image, can obtain the statistical information of track parameter.
Some solid state nuclear track Processing Algorithm and automatic measurement systems have appearred at present both at home and abroad, obtain the ichnography picture after, or image carried out a series of analyzing and processing such as pre-service, binaryzation, adherence Separation, or behind the analyzing and processing image, measures the parameter information of track.Key problem is adherence Separation in the analyzing and processing, and the result of separation and time efficient will have a strong impact on the performance of parameter measurement precision and system.The TRIAC of D.L.Patiris etc. and TRIACII adopt K-means method split image, justify detection with the hough conversion again, and operand is very big, is prone to undetected and flase drop.Deng Fuwei, the ring of younger brother's space, Ye Hongbing etc. adopt Otsu binaryzation ichnography picture, seek burble point according to the result of corrosion or range conversion, and the separation of synechia track is prone to undetectedly, can not well keep the original-shape of track.The TractTest software of Zhang Qingxian etc. adopts corrosion plavini separation of synechia track, intensive track is carried out adherence Separation be prone to undetectedly, and parameter measurement is accurate not.The software TRANA of Labview language compilation such as F.Coppola, can distinguish track and surface scratch and other impurity, separation, the overlapping track group in test section, can measure geometric properties and the brightness such as center, radius, area of nuclear track, but the method can only be separated the overlapping track that two kinds of centers approach.
The basic parameter of solid state nuclear track after etching can be with simple geometry figure explanation, as shown in Figure 1, particle is incident in detector surface S with the θ angle, detector surface becomes S ' after the etching, track is conical hole, dip of the track is H, and the surface opening profile is oval, and major and minor axis is respectively Mi and Mj.
The solid state nuclear track micro-image has following features:
(1) particle density is high.As under 20 times of zoom microscopes, when image resolution ratio is the 344nm/ pixel, 1cm
2The image size of track sheet reach 1.72 GB, the track number is 2*10 approximately
5Individual.
(2) the track adhesion is serious.The reason such as high owing to particle density, that randomness is strong, the track adhesion is serious.
(3) track granularity difference is large.The track approximate ellipsoidal, its radius can be from 1 μ m to 20 μ m.
(4) the track interior intensity is inhomogeneous.The intensity profile of track and center hole thereof is inhomogeneous.
(5) there is non-track impurity.Ichnography looks like to exist bubble, cut and other non-track impurity.
This paper based on Mathematical Morphology Method, has proposed a kind of intensive solid state nuclear track micro-image adherence Separation algorithm for the problem of present solid state nuclear track adherence Separation algorithm existence and the characteristics of solid state nuclear track micro-image.
Summary of the invention
Technical matters to be solved by this invention is the adherence Separation algorithm that a kind of packed solid nuclear track is provided for the deficiencies in the prior art.
Technical scheme of the present invention is as follows:
A kind of adherence Separation algorithm of packed solid nuclear track may further comprise the steps:
(1) picture contrast strengthens: to entire image normalization and expand to the 0-255 scope, in the situation that do not introduce noise, strengthen the grey-scale contrast of light grey little track and background;
(2) expansion maximum value is cut apart:
After strengthening the contrast of image, adopt expansion maximum value split plot design that image is carried out geodetic and rebuild, reconstructed results figure is carried out the conversion of H maximum value, transformation results is carried out regional maximum value conversion, binaryzation ichnography picture obtains initial track connected region again; And in conjunction with the threshold value of form factor and area, remove non-track impurity;
(3) area ratio adherence Separation:
For the pertusate initial track connected region of segmentation result image inside center, adopt expand each hole of initial connected region of morphological method iteration, when the hole original track corresponding with it overlaps substantially, stop to expand, the hole profile is carried out ellipse fitting, and the profile of hole namely can be used as the profile of original track at this moment; Each hole is processed equally, can be obtained the profile of single track in the adhesion track, thus the separation of synechia track;
(4) special adherence Separation.
Described adherence Separation algorithm, described adherence Separation algorithm concrete steps are: 1. reduce first the gray scale of view picture solid state nuclear track image F1, obtain image F2, F2 is normalized in the 0-1 scope, multiply by 255 again, obtain image F3;
2. adopt expansion maximum value partitioning algorithm with image binaryzation to strengthening image F3, obtain initial track connected region profile, calculate the form factor PE of connected region, suc as formula (1);
PE=4πA/C
2（1）
Wherein, A is the area of profile place connected domain, and C is the girth of profile place connected domain;
3. for form factor PE and area A arrange respectively threshold value T1 and T2, if PE greater than T1 and A greater than T2, then connected region is track, otherwise connected region is the impurity of non-track, removes the impurity of non-track, obtains split image F4;
4. to pertusate each the initial connected region Oi of the inner tool of split image F4, fill hole and obtain blank map, extract one of them hole Hi and obtain hole figure;
5. calculate the area A rea (Hi) of hole, hole figure and blank map are sought common ground, calculate the area A rea (Hi ∩ Oi) that occurs simultaneously;
6. judge hole and the area of common factor ratio Area (Hi)/whether Area (Hi ∩ Oi) greater than 1, if be not more than 1, then hole is less than its corresponding track, and hole is once expanded, and returns 5.; Otherwise, expand and finish, extract the hole profile, profile is carried out ellipse fitting, namely obtain the profile of single track;
7. adopt order 4.-6. that pertusate all the initial connected regions of the inner tool of split image F4 are processed, can obtain the profile of the pertusate track of the inner tool of all images;
8. for the initial track connected region at image border place, extract its initial track connected region after, replenish imperfect hole breach, take at the edge as axis of symmetry, connected region is carried out symmetry subsidizes, fill the true hole that subsidizes rear track target;
9. the figure that symmetry is subsidized and filled behind the hole carries out the city block distance conversion, size take the distance value at hole core place as morphological structuring elements, the expansion hole extracts the hole profile and also carries out ellipse fitting, can obtain the profile of single track, thus the separation of synechia track;
10. single without the hole track to image inside carries out Gaussian smoothing with the template of 3*3 to its profile, and the result after then will be level and smooth is as the profile of single track.
Algorithm of the present invention can effectively solve the accurate separation problem of the track that processing, adhesion are serious, interior intensity is inhomogeneous of the removal of noise in the ichnography picture and non-track impurity, track that granularity difference is large, can promote adherence Separation speed simultaneously.
Because track sheet chemical etching condition and microscope gather the similarities and differences of ichnography image quality, cause ichnography to look like that different is arranged.In image is processed, the reduction value of gray scale can be revised during contrast strengthened, expansion maximum value is cut apart and the threshold value of removing the impurity track can arrange as the case may be, area ratio separates the structural element of expansion process can select different shape and size, Gauss's template is optional selects different sizes, and when carrying out range conversion, can adopt other range conversions, such as non-Euclidean distance chessboard distance commonly used, chamfering distance etc.
Description of drawings
Fig. 1 is etching tracks geometry sketch, and a is vertical cross section, and b is the surface opening profile diagram;
Fig. 2 is packed solid nuclear track adherence Separation algorithmic procedure figure;
Fig. 3 is experiment effect figure, (a) the former figure of solid state nuclear track, (b) expansion maximum value cut apart and impurity elimination after image, (c) adherence Separation rear profile figure;
Embodiment
Below in conjunction with specific embodiment, the present invention is described in detail.
For problem demanding prompt solution in the solid state nuclear track image, a kind of adherence Separation method of packed solid nuclear track has been proposed.The method strengthens track micro-image degree of comparing first; Adopt again expansion maximum value split plot design split image, obtain initial track target; Then adopt the adhesion track of mathematical morphology and area ratio method separate picture inside; And the track at edge place and imperforate single track carry out special adherence Separation.Algorithmic procedure figure as shown in Figure 2.
(1) picture contrast strengthens
The track granularity differs greatly in the image, track is grey black mostly, and some little tracks are light grey, approach with the background impurities gray scale, therefore adopt a kind of image enchancing method of Simple fast, reduce the gray scale of view picture track micro-image, to entire image normalization and expand to the 0-255 scope, in the situation that do not introduce noise, strengthen the grey-scale contrast of light grey little track and background.
(2) expansion maximum value is cut apart
After strengthening the contrast of image, adopt expansion maximum value split plot design that image is carried out geodetic and rebuild, reconstructed results figure is carried out the conversion of H maximum value, transformation results is carried out regional maximum value conversion, binaryzation ichnography picture obtains initial track connected region again; And in conjunction with the threshold value of form factor and area, remove non-track impurity.
(3) area ratio adherence Separation (corresponding concrete steps 4.～7.)
For the pertusate initial track connected region of segmentation result image inside center, adopt expand each hole of initial connected region of morphological method iteration, when the hole original track corresponding with it overlaps substantially, stop to expand, the hole profile is carried out ellipse fitting, and the profile of hole namely can be used as the profile of original track at this moment; Each hole is processed equally, can be obtained the profile of single track in the adhesion track, thus the separation of synechia track.
(4) special adherence Separation (corresponding concrete steps 8.～10.)
4.1 single adherence Separation without the hole track
For the inner imperforate single track of segmentation result image, there is not adhesion in itself, but the normal indentation of its profile, therefore the track profile that extracts is carried out Gaussian smoothing, with the profile of the result after level and smooth as single track.
4.2 the adherence Separation of place, image border track
At the place, image border, track has 5 kinds of situations: there is adhesion in track, and track is substantially complete, and hole is complete; There is adhesion in track, and track is by cutting, and hole is complete; There is not adhesion in track, and track is by cutting, and hole is complete; There is not adhesion in track, and track and hole are all by cutting, and hole is imperfect; There is not adhesion in track, and track is by cutting, and remaining fraction track is without hole.Need to adopt the track at the method separation edge places such as additional breach, symmetry are subsidized, range conversion, morphological dilations.
Concrete steps are as follows:
1. reduce first the gray scale of view picture solid state nuclear track image F1, obtain image F2, F2 is normalized in the 0-1 scope, multiply by again 255, obtain image F3.
2. adopt expansion maximum value partitioning algorithm with image binaryzation to strengthening image F3, obtain initial track connected region profile, calculate the form factor PE of connected region, suc as formula (1).
PE=4πA/C
2（1）
Wherein, A is the area of profile place connected domain, and C is the girth of profile place connected domain.
3. threshold value T1(span is set respectively between 0 ~ 1 for form factor PE and area A) and T2, if PE greater than T1 and A greater than T2, then connected region is track, otherwise connected region is the impurity of non-track, removes the impurity of non-track, obtains split image F4.
4. to pertusate each the initial connected region Oi of the inner tool of split image F4, fill hole and obtain blank map, extract one of them hole Hi and obtain hole figure.
5. calculate the area A rea (Hi) of hole, hole figure and blank map are sought common ground, calculate the area A rea (Hi ∩ Oi) that occurs simultaneously.
6. judge hole and the area of common factor ratio Area (Hi)/whether Area (Hi ∩ Oi) greater than 1, if be not more than 1, then hole is less than its corresponding track, and hole is once expanded, and returns 5.; Otherwise, expand and finish, extract the hole profile, profile is carried out ellipse fitting, namely obtain the profile of single track.
7. adopt order 4.-6. that pertusate all the initial connected regions of the inner tool of split image F4 are processed, can obtain the profile of the pertusate track of the inner tool of all images.
8. for the initial track connected region at image border place, extract its initial track connected region after, replenish imperfect hole breach, take at the edge as axis of symmetry, connected region is carried out symmetry subsidizes, fill the true hole that subsidizes rear track target.
9. the figure that symmetry is subsidized and filled behind the hole carries out the city block distance conversion, size take the distance value at hole core place as morphological structuring elements, the expansion hole extracts the hole profile and also carries out ellipse fitting, can obtain the profile of single track, thus the separation of synechia track.
10. single without the hole track to image inside carries out Gaussian smoothing with the template of 3*3 to its profile, and the result after then will be level and smooth is as the profile of single track.
Adopt as above algorithm flow, its experimental result as shown in Figure 3.
(1) when contrast strengthens, need to reduce the integral image gray scale, suggestion reduction value is about 100, this value is relevant with the average gray of concrete ichnography picture.
(2) when the area ratio adherence Separation, the structural element that expansive working is used is larger, separates the profile that the obtains true profile of more can not fitting, and therefore, suggestion structural element cut-off directly is 2 or 4 circle.
(3) when the track to image border place carries out adherence Separation, need to replenish imperfect hole breach, if supplementary cords is excessively thick, can make the track hole too small and can not carry out ellipse fitting, therefore, the suggestion supplementary cords slightly is 1 pixel.
(4) in experiment, the H value in the conversion of H maximum value, form factor threshold value Τ 1 and area Τ 2 are taken as respectively 70,0.28 and 95.
Should be understood that, for those of ordinary skills, can be improved according to the above description or conversion, and all these improvement and conversion all should belong to the protection domain of claims of the present invention.
Claims (2)
1. the adherence Separation algorithm of a packed solid nuclear track, it is characterized in that, may further comprise the steps: (1) picture contrast strengthens: to entire image normalization and expand to the 0-255 scope, in the situation that do not introduce noise, strengthen the grey-scale contrast of light grey little track and background;
(2) expansion maximum value is cut apart:
After strengthening the contrast of image, adopt expansion maximum value split plot design that image is carried out geodetic and rebuild, reconstructed results figure is carried out the conversion of H maximum value, transformation results is carried out regional maximum value conversion, binaryzation ichnography picture obtains initial track connected region again; And in conjunction with the threshold value of form factor and area, remove non-track impurity;
(3) area ratio adherence Separation:
For the pertusate initial track connected region of segmentation result image inside center, adopt expand each hole of initial connected region of morphological method iteration, when the hole original track corresponding with it overlaps substantially, stop to expand, the hole profile is carried out ellipse fitting, and the profile of hole namely can be used as the profile of original track at this moment; Each hole is processed equally, can be obtained the profile of single track in the adhesion track, thus the separation of synechia track;
(4) special adherence Separation.
2. adherence Separation algorithm according to claim 1 is characterized in that, described adherence Separation algorithm concrete steps are: the gray scale that 1. reduces first view picture solid state nuclear track image F1, obtain image F2, F2 is normalized in the 0-1 scope, multiply by again 255, obtain image F3;
2. adopt expansion maximum value partitioning algorithm with image binaryzation to strengthening image F3, obtain initial track connected region profile, calculate the form factor PE of connected region, suc as formula (1);
PE=4πA/C
2（1）
Wherein, A is the area of profile place connected domain, and C is the girth of profile place connected domain;
3. for form factor PE and area A arrange respectively threshold value T1 and T2, if PE greater than T1 and A greater than T2, then connected region is track, otherwise connected region is the impurity of non-track, removes the impurity of non-track, obtains split image F4;
4. to pertusate each the initial connected region Oi of the inner tool of split image F4, fill hole and obtain blank map, extract one of them hole Hi and obtain hole figure;
5. calculate the area A rea (Hi) of hole, hole figure and blank map are sought common ground, calculate the area A rea (Hi ∩ Oi) that occurs simultaneously;
6. judge hole and the area of common factor ratio Area (Hi)/whether Area (Hi ∩ Oi) greater than 1, if be not more than 1, then hole is less than its corresponding track, and hole is once expanded, and returns 5.; Otherwise, expand and finish, extract the hole profile, profile is carried out ellipse fitting, namely obtain the profile of single track;
7. adopt order 4.-6. that pertusate all the initial connected regions of the inner tool of split image F4 are processed, can obtain the profile of the pertusate track of the inner tool of all images;
8. for the initial track connected region at image border place, extract its initial track connected region after, replenish imperfect hole breach, take at the edge as axis of symmetry, connected region is carried out symmetry subsidizes, fill the true hole that subsidizes rear track target;
9. the figure that symmetry is subsidized and filled behind the hole carries out the city block distance conversion, size take the distance value at hole core place as morphological structuring elements, the expansion hole extracts the hole profile and also carries out ellipse fitting, can obtain the profile of single track, thus the separation of synechia track;
10. single without the hole track to image inside carries out Gaussian smoothing with the template of 3*3 to its profile, and the result after then will be level and smooth is as the profile of single track.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210584294.8A CN103065283B (en) | 2012-12-28 | 2012-12-28 | A kind of adherence Separation method of packed solid nuclear track |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210584294.8A CN103065283B (en) | 2012-12-28 | 2012-12-28 | A kind of adherence Separation method of packed solid nuclear track |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103065283A true CN103065283A (en) | 2013-04-24 |
| CN103065283B CN103065283B (en) | 2015-09-09 |
Family
ID=48107900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210584294.8A Expired - Fee Related CN103065283B (en) | 2012-12-28 | 2012-12-28 | A kind of adherence Separation method of packed solid nuclear track |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103065283B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894512A (en) * | 2016-03-31 | 2016-08-24 | 中国农业大学 | Adhesive corn ear segmentation method and device used in cell corn ear species testing |
| CN106203456A (en) * | 2016-07-20 | 2016-12-07 | 西安科技大学 | Coal dust Algorithm for Overlapping Granule separation method based on improved differential evolution particle cluster algorithm |
| CN111179236A (en) * | 2019-12-23 | 2020-05-19 | 湖南长天自控工程有限公司 | Raw ball granularity analysis method and device for pelletizer |
| CN111327783A (en) * | 2014-04-30 | 2020-06-23 | 虹光精密工业股份有限公司 | Transaction machine with image processing function |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009128267A (en) * | 2007-11-27 | 2009-06-11 | Toyobo Co Ltd | Image processing method |
| CN101692282A (en) * | 2009-10-16 | 2010-04-07 | 浙江工业大学 | Morphology based method for separating cells |
-
2012
- 2012-12-28 CN CN201210584294.8A patent/CN103065283B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009128267A (en) * | 2007-11-27 | 2009-06-11 | Toyobo Co Ltd | Image processing method |
| CN101692282A (en) * | 2009-10-16 | 2010-04-07 | 浙江工业大学 | Morphology based method for separating cells |
Non-Patent Citations (4)
| Title |
|---|
| CECILIA DI RUBERTOT, ET AL: "Segmentation of Blood Images Using Morphological Operators", 《PROCEEDINGS OF IEEE 15TH INTERNATION CONFORENCE ON PATTERN RECOGNITION》 * |
| XIANGBIN LIU ET AL: "A New Approach to Separating Touching Spots in Particle Images", 《PROCEEDINGS OF 2004 INTERNATIONAL SYMPOSIUM ON INTELLIGENT MULTIMEDIA. VIDEO AND SPEECH PROCESSING》 * |
| 张洁等: "粘连细胞分离算法综述", 《计算机与数字工程》 * |
| 过惠平等: "基于流域算法的重叠核径迹图像分割方法研究", 《核科学与工程》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111327783A (en) * | 2014-04-30 | 2020-06-23 | 虹光精密工业股份有限公司 | Transaction machine with image processing function |
| CN111327783B (en) * | 2014-04-30 | 2022-02-25 | 虹光精密工业股份有限公司 | Transaction machine with image processing function |
| CN105894512A (en) * | 2016-03-31 | 2016-08-24 | 中国农业大学 | Adhesive corn ear segmentation method and device used in cell corn ear species testing |
| CN105894512B (en) * | 2016-03-31 | 2019-03-01 | 中国农业大学 | Adhesion corn ear dividing method and device in a kind of cell corn ear test |
| CN106203456A (en) * | 2016-07-20 | 2016-12-07 | 西安科技大学 | Coal dust Algorithm for Overlapping Granule separation method based on improved differential evolution particle cluster algorithm |
| CN111179236A (en) * | 2019-12-23 | 2020-05-19 | 湖南长天自控工程有限公司 | Raw ball granularity analysis method and device for pelletizer |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103065283B (en) | 2015-09-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103136528B (en) | A kind of licence plate recognition method based on dual edge detection | |
| CN103927526B (en) | Vehicle detecting method based on Gauss difference multi-scale edge fusion | |
| CN102044069B (en) | Method for segmenting white blood cell image | |
| CN107256558A (en) | The cervical cell image automatic segmentation method and system of a kind of unsupervised formula | |
| CN103049750B (en) | Character identifying method | |
| CN102968646B (en) | A kind of detection method of license plate based on machine learning | |
| CN109145756A (en) | Object detection method based on machine vision and deep learning | |
| CN202084185U (en) | Automatic traffic sign identification device | |
| CN102676633A (en) | Method for automatically counting bacterial colonies | |
| CN103345748B (en) | A kind of locating segmentation method of human tissue cell two-photon micro-image | |
| CN102609917B (en) | Image edge fitting B spline generating method based on clustering algorithm | |
| CN103065283A (en) | Adherence separation algorithm of intensive solid state nuclear tracks | |
| CN103839279A (en) | Adhesion object segmentation method based on VIBE in object detection | |
| CN103971135A (en) | Human body target detection method based on head and shoulder depth information features | |
| CN104134219A (en) | Color image segmentation algorithm based on histograms | |
| CN103942797A (en) | Scene image text detection method and system based on histogram and super-pixels | |
| CN101576958A (en) | Extraction method of rectangle seal graphics with border based on form feature | |
| CN103400113B (en) | Freeway tunnel pedestrian detection method based on image procossing | |
| CN104463138A (en) | Text positioning method and system based on visual structure attribute | |
| CN102073852A (en) | Multiple vehicle segmentation method based on optimum threshold values and random labeling method for multiple vehicles | |
| CN104732229A (en) | Segmentation method for overlapping cells in cervical smear image | |
| CN107578048A (en) | A kind of long sight scene vehicle checking method based on vehicle rough sort | |
| CN106875407A (en) | A kind of unmanned plane image crown canopy dividing method of combining form and marking of control | |
| Ok | Automated extraction of buildings and roads in a graph partitioning framework | |
| CN102854147A (en) | Hyperspectral data based mural manuscript information extraction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150909 Termination date: 20151228 |
|
| EXPY | Termination of patent right or utility model |